通过量化模型对不良知识的自信度，实现更精准的遗忘而不丢失有用能力。
CALIBURN: Self-Calibrated LLM Unlearning Alignment
- 用自信度校准遗忘梯度，避免盲目删除
- 在多个基准上实现更好遗忘效果与性能平衡
- 大幅减少对保留数据的需求，适合实际部署
大语言模型遗忘旨在移除预训练语言模型中的不良知识，为应对安全与隐私问题提供实用机制。现有方法如梯度上升易导致灾难性遗忘；基于对齐的方法则受限于参考模型质量。在真实场景中，两者仍需大量保留数据以维护通用知识。本文提出一种原则性方法，通过量化目标模型对不良知识的置信度，更精确地校准遗忘梯度更新，实现细粒度控制遗忘过程，同时更好保留模型实用性，从而降低对保留数据或海量遗忘训练数据的依赖。在MUSE和WMDP等多个基准上的广泛评估表明，本方法在有效遗忘的同时，优于当前最优方法，在知识清除与能力保留之间取得更优权衡。
原文摘要 · Abstract (English)
LLM unlearning aims to remove the influence of undesirable knowledge from pretrained language models, which offers a practical mechanism for addressing safety and privacy concerns. Existing unlearning approaches, such as Gradient Ascent, are prone to catastrophic forgetting. Alignment-based approaches provide an alternative direction, yet their effectiveness is limited by the quality of the reference model. In realistic settings, both methods still require large retention datasets to preserve general knowledge. We propose a principled method that quantifies the target LLM's confidence in undesirable knowledge and uses it to calibrate the model's unlearning gradient updates more precisely. It enables fine-grained control over forgetting while better preserving model utility, thus reducing the dependence on retention data or prohibitive unlearning training data. Extensive evaluations on multiple benchmarks, including MUSE and WMDP, show that our method achieves effective unlearning and improves the trade-off between knowledge removal and utility preservation compared with state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。